{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F2E762HS25FSIDYYI4O4EBHWLJ","short_pith_number":"pith:F2E762HS","schema_version":"1.0","canonical_sha256":"2e89ff68f2d74b240f18471dc204f65a59197f7c361d5b3111d937dea6f04e9c","source":{"kind":"arxiv","id":"2504.00226","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models in Numberland: A Quick Test of Their Numerical Reasoning Abilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Roussel Rahman","submitted_at":"2025-03-31T21:06:39Z","abstract_excerpt":"An essential element of human mathematical reasoning is our number sense -- an abstract understanding of numbers and their relationships -- which allows us to solve problems involving vast number spaces using limited computational resources. Mathematical reasoning of Large Language Models (LLMs) is often tested on high-level problems (such as Olympiad challenges, geometry, word problems, and puzzles), but their low-level number sense remains less explored. We introduce \"Numberland,\" a 100-problem test to evaluate the numerical reasoning abilities of LLM-based agents. The tasks -- basic operati"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.00226","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-31T21:06:39Z","cross_cats_sorted":[],"title_canon_sha256":"dc2dbf0ed24805517ad06a694e504e868e978ad4baad2827e17f1368055563ab","abstract_canon_sha256":"4c9fd57b966d90098e21a82c7ebfe43d48f11b85efbf57c017b78c6a9c13e95d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:22.067457Z","signature_b64":"thaY4lSDDvoailnc2lS3weAmjBlxBpX4kDnUJOclxg22Yup9K0En9TcxFQtR/e8oxOOnnxhLkBjpX1z7GnuoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e89ff68f2d74b240f18471dc204f65a59197f7c361d5b3111d937dea6f04e9c","last_reissued_at":"2026-07-05T10:42:22.067052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:22.067052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models in Numberland: A Quick Test of Their Numerical Reasoning Abilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Roussel Rahman","submitted_at":"2025-03-31T21:06:39Z","abstract_excerpt":"An essential element of human mathematical reasoning is our number sense -- an abstract understanding of numbers and their relationships -- which allows us to solve problems involving vast number spaces using limited computational resources. Mathematical reasoning of Large Language Models (LLMs) is often tested on high-level problems (such as Olympiad challenges, geometry, word problems, and puzzles), but their low-level number sense remains less explored. We introduce \"Numberland,\" a 100-problem test to evaluate the numerical reasoning abilities of LLM-based agents. The tasks -- basic operati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00226","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.00226/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.00226","created_at":"2026-07-05T10:42:22.067111+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.00226v1","created_at":"2026-07-05T10:42:22.067111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00226","created_at":"2026-07-05T10:42:22.067111+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2E762HS25FS","created_at":"2026-07-05T10:42:22.067111+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2E762HS25FSIDYY","created_at":"2026-07-05T10:42:22.067111+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2E762HS","created_at":"2026-07-05T10:42:22.067111+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.04023","citing_title":"Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language Models","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F2E762HS25FSIDYYI4O4EBHWLJ","json":"https://pith.science/pith/F2E762HS25FSIDYYI4O4EBHWLJ.json","graph_json":"https://pith.science/api/pith-number/F2E762HS25FSIDYYI4O4EBHWLJ/graph.json","events_json":"https://pith.science/api/pith-number/F2E762HS25FSIDYYI4O4EBHWLJ/events.json","paper":"https://pith.science/paper/F2E762HS"},"agent_actions":{"view_html":"https://pith.science/pith/F2E762HS25FSIDYYI4O4EBHWLJ","download_json":"https://pith.science/pith/F2E762HS25FSIDYYI4O4EBHWLJ.json","view_paper":"https://pith.science/paper/F2E762HS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.00226&json=true","fetch_graph":"https://pith.science/api/pith-number/F2E762HS25FSIDYYI4O4EBHWLJ/graph.json","fetch_events":"https://pith.science/api/pith-number/F2E762HS25FSIDYYI4O4EBHWLJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2E762HS25FSIDYYI4O4EBHWLJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2E762HS25FSIDYYI4O4EBHWLJ/action/storage_attestation","attest_author":"https://pith.science/pith/F2E762HS25FSIDYYI4O4EBHWLJ/action/author_attestation","sign_citation":"https://pith.science/pith/F2E762HS25FSIDYYI4O4EBHWLJ/action/citation_signature","submit_replication":"https://pith.science/pith/F2E762HS25FSIDYYI4O4EBHWLJ/action/replication_record"}},"created_at":"2026-07-05T10:42:22.067111+00:00","updated_at":"2026-07-05T10:42:22.067111+00:00"}